© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9010
    Prev
    Next
    INDEX
    Explanations

    female relatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.41
     iVar
    -0.41
     أبريل
    -0.39
    vaného
    -0.39
     fédé
    -0.38
    belajaran
    -0.37
    lungen
    -0.36
     Rück
    -0.36
     asiatique
    -0.35
     vétérina
    -0.35
    POSITIVE LOGITS
     урна
    0.85
    rawDesc
    0.79
    EndInit
    0.75
     ProtoMessage
    0.71
     متعلقه
    0.67
     defaultstate
    0.66
    IsContent
    0.65
    bootstrapcdn
    0.65
     resourceCulture
    0.64
    InstrumentedTest
    0.64
    Activations Density 0.009%

    No Known Activations